Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method and device for recognizing speaker-independent isolated word based on subspace

A non-specific person and subspace technology, applied in speech recognition, speech analysis, instruments, etc., can solve problems such as inaccurate estimation and many Markov model parameters.

Inactive Publication Date: 2012-09-26
BEIJING DAMINGHUI TECH
View PDF4 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0015] The purpose of the present invention is to: propose a non-specific human isolated word recognition method and device based on subspace technology to solve the problem that there are many parameters in the hidden Markov model in the traditional method and cannot be accurately estimated

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method and device for recognizing speaker-independent isolated word based on subspace
  • Method and device for recognizing speaker-independent isolated word based on subspace
  • Method and device for recognizing speaker-independent isolated word based on subspace

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] Method of the present invention is realized by following steps in digital integrated circuit chip:

[0047] Step 1: Front-end processing module, including voice enhancement sub-module, active voice detection sub-module and voice cutting sub-module.

[0048] Step 1.1: Speech enhancement sub-module, using frequency-domain Wiener filtering to suppress non-speech parts to a certain extent;

[0049] Step 1.2: the active speech detection submodule adopts G723.9 to mark the time index of speech and non-speech;

[0050] Step 1.3: Speech segmentation sub-module, frame the speech for subsequent feature extraction.

[0051] Step 2: Feature extraction module, including extracting basic feature sub-module and differential sub-module.

[0052] Step 2.1: Extract basic features sub-module: extract 12-dimensional MFCC basic features and energy to form 13-dimensional basic features;

[0053] Step 2.2: The difference sub-module uses the basic features to construct the first-order and s...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to the field of automatic speech recognition, and especially to a method and a device for recognizing speaker-independent isolated words based on subspace. The method is characterized by applying subspace technology into a hidden Markov model and comprises the steps of: first, using all speech data to train a global model, then, adopting a method of subspace self-adaption to describe an acoustic element model, and establishing a hidden Markov model accordingly. The device consists of a voice preprocessing module, a feature extraction module, a model building module, a model matching module and a score decision module. The method and the device provided by the invention are capable of making a robust valuation under the condition of limited data, and are suitable for recognizing speaker-independent isolated words of a medium-scale vocabulary under the condition of limited speech data training and recognition.

Description

technical field [0001] The invention relates to the field of automatic speech recognition, in particular, a method and device for identifying non-specific isolated words based on subspace technology. Background technique [0002] Voice is the most natural, flexible and frequent way for human beings to communicate information. Speech contains multiple layers of information, how to automatically extract this information has become the main research content in the field of speech signal processing. As an important branch of this field, Isolated Word Recognition (IWR) is a recognition technology that uses computers to automatically extract content from speech fragments. It is widely used in many fields such as car navigation, computer control, and toys. [0003] At present, non-specific person isolated word recognition mainly uses the method of statistical pattern recognition, which is divided into two stages of training and testing. The training phase can be divided into thre...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G10L15/06G10L15/14
Inventor 何亮巴福生
Owner BEIJING DAMINGHUI TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com